This code analyses splitting statistics for CTC-clusters.
The analysis takes a list of trees sampled from its posterior distribution as input and samples mutations placements for each of the trees.
inputFolder <- "/Users/jgawron/Documents/projects/CTC_backup/input_folder"
simulationInputFolder <- "/Users/jgawron/Documents/projects/CTC_backup/simulations/simulations2"
treeName <- "Br16_AC"
nTreeSamplingEvents <- 1000
nMutationSamplingEvents <- 1000
source("/Users/jgawron/Documents/projects/CTC-SCITE/CTC-SCITE/experiments/workflow/resources/functions.R")
## ── Attaching core tidyverse packages ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
input <- load_data(inputFolder, treeName)
## Rows: 40000 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (1): Tree
## dbl (4): LogScore, SequencingErrorRate, DropoutRate, LogTau
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 557 Columns: 72
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (3): X1, X3, X4
## dbl (69): X2, X5, X6, X7, X8, X9, X10, X11, X12, X13, X14, X15, X16, X17, X1...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 34 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (2): Cluster, Description
## dbl (3): CellCount, TCs, WBCs
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
postSampling <- input$postSampling
nClusters <- input$nClusters
ClusterID <- input$clusterID
nCells <- input$nCells
nMutations <- input$nMutations
nClusters <- input$nClusters
alleleCount <- input$alleleCount
mutatedReadCounts <- input$mutatedReadCounts
totalReadCounts <- input$totalReadCounts
sampleDescription <- input$sample_description
Each row corresponds to a cell. Column description: - Cluster: An number indicating which sample the cell belongs to. - ClusterName: The name of the sample in the nodeDescription.tsv file - WBC: a binary vector indicating whether the cell is a white blood cell (1) or not (0). - color: Indicates the color of the cluster in the tree, as described in the nodeDescription.tsv file.
print(sampleDescription)
## Cluster ClusterName WBC color single_cell
## 1 0 Br16_AC1 0 lightcoral FALSE
## 2 0 Br16_AC1 0 lightcoral FALSE
## 3 0 Br16_AC1 0 lightcoral FALSE
## 4 1 Br16_AC10 0 gray93 TRUE
## 5 2 Br16_AC12 0 sandybrown TRUE
## 6 3 Br16_AC13 0 sandybrown TRUE
## 7 4 Br16_AC14 0 skyblue3 FALSE
## 8 4 Br16_AC14 0 skyblue3 FALSE
## 9 5 Br16_AC15 0 thistle FALSE
## 10 5 Br16_AC15 0 thistle FALSE
## 11 6 Br16_AC16 0 lemonchiffon FALSE
## 12 6 Br16_AC16 0 lemonchiffon FALSE
## 13 6 Br16_AC16 0 lemonchiffon FALSE
## 14 7 Br16_AC17 0 violetred3 FALSE
## 15 7 Br16_AC17 0 violetred3 FALSE
## 16 7 Br16_AC17 0 violetred3 FALSE
## 17 7 Br16_AC17 0 violetred3 FALSE
## 18 8 Br16_AC18 0 lightslateblue FALSE
## 19 8 Br16_AC18 0 lightslateblue FALSE
## 20 9 Br16_AC19 0 gray93 TRUE
## 21 10 Br16_AC20 0 deeppink FALSE
## 22 10 Br16_AC20 0 deeppink FALSE
## 23 10 Br16_AC20 0 deeppink FALSE
## 24 11 Br16_AC21 0 gray93 TRUE
## 25 12 Br16_AC22 0 mediumaquamarine FALSE
## 26 12 Br16_AC22 0 mediumaquamarine FALSE
## 27 12 Br16_AC22 0 mediumaquamarine FALSE
## 28 13 Br16_AC24 0 mistyrose FALSE
## 29 13 Br16_AC24 0 mistyrose FALSE
## 30 14 Br16_AC25 0 gray93 TRUE
## 31 15 Br16_AC26 0 gray93 TRUE
## 32 16 Br16_AC27 0 powderblue FALSE
## 33 16 Br16_AC27 0 powderblue FALSE
## 34 17 Br16_AC28 0 steelblue FALSE
## 35 17 Br16_AC28 0 steelblue FALSE
## 36 17 Br16_AC28 0 steelblue FALSE
## 37 18 Br16_AC29 0 gray93 TRUE
## 38 19 Br16_AC3 0 paleturquoise3 FALSE
## 39 19 Br16_AC3 0 paleturquoise3 FALSE
## 40 19 Br16_AC3 0 paleturquoise3 FALSE
## 41 20 Br16_AC30 0 greenyellow FALSE
## 42 20 Br16_AC30 0 greenyellow FALSE
## 43 21 Br16_AC33 0 khaki3 FALSE
## 44 21 Br16_AC33 0 khaki3 FALSE
## 45 22 Br16_AC34 0 darkseagreen4 FALSE
## 46 22 Br16_AC34 0 darkseagreen4 FALSE
## 47 23 Br16_AC35 0 gold TRUE
## 48 24 Br16_AC37 0 plum FALSE
## 49 24 Br16_AC37 0 plum FALSE
## 50 25 Br16_AC38 0 yellowgreen TRUE
## 51 26 Br16_AC39 0 yellowgreen FALSE
## 52 26 Br16_AC39 0 yellowgreen FALSE
## 53 26 Br16_AC39 0 yellowgreen FALSE
## 54 27 Br16_AC4 0 navajowhite2 FALSE
## 55 27 Br16_AC4 0 navajowhite2 FALSE
## 56 28 Br16_AC40 0 crimson FALSE
## 57 28 Br16_AC40 0 crimson FALSE
## 58 28 Br16_AC40 0 crimson FALSE
## 59 28 Br16_AC40 0 crimson FALSE
## 60 28 Br16_AC40 0 crimson FALSE
## 61 29 Br16_AC5 0 gray93 TRUE
## 62 30 Br16_AC6 0 gray93 TRUE
## 63 31 Br16_AC7 0 cadetblue FALSE
## 64 31 Br16_AC7 0 cadetblue FALSE
## 65 31 Br16_AC7 0 cadetblue FALSE
## 66 31 Br16_AC7 0 cadetblue FALSE
## 67 32 Br16_AC8 0 darkslategray FALSE
## 68 32 Br16_AC8 0 darkslategray FALSE
## 69 32 Br16_AC8 0 darkslategray FALSE
## 70 33 Br16_AC9 0 gray93 TRUE
Get null distributions of relevant statistics, stratified by sample:
cutoffsSplittingProbs <- data.frame(clusterSize = vector(), Cutoff = vector())
cutoffsBranchingProbabilities <- data.frame(clusterSize = vector(), Cutoff = vector())
for (clusterSize in 2:5){
try(
{treeNameSimulated <- paste(treeName, clusterSize, sep = '_')
inputSimulated <- load_data(simulationInputFolder, treeNameSimulated)
postSamplingSimulated <- inputSimulated$postSampling
nClustersSimulated <- inputSimulated$nClusters
ClusterIDSimulated <- inputSimulated$clusterID
nCellsSimulated <- inputSimulated$nCells
nMutationsSimulated <- inputSimulated$nMutations
nClustersSimulated <- inputSimulated$nClusters
alleleCountSimulated <- inputSimulated$alleleCount
mutatedReadCountsSimulated <- inputSimulated$mutatedReadCounts
totalReadCountsSimulated <- inputSimulated$totalReadCounts
sampleDescriptionSimulated <- inputSimulated$sample_description
distance <- computeClusterSplits(sampleDescriptionSimulated, postSamplingSimulated, treeNameSimulated, nCellsSimulated,
nMutationsSimulated, nClustersSimulated,
alleleCountSimulated,
mutatedReadCountsSimulated, totalReadCountsSimulated,
nMutationSamplingEvents = nMutationSamplingEvents, nTreeSamplingEvents = nTreeSamplingEvents,
cellPairSelection = c("orchid", "orchid1", "orchid2",
"orchid3", "orchid4", "darkorchid",
"darkorchid1","darkorchid2", "darkorchid3",
"darkorchid4", "purple", "purple1",
"purple2", "purple3", "purple4"))
plot(ggplot(distance$splittingProbs, aes(x = "Values", y = Splitting_probability, fill = 'Splitting_probability')) +
geom_boxplot())
cutoffsSplittingProbs <- rbind(cutoffsSplittingProbs, data.frame(clusterSize = clusterSize, Cutoff = mean(distance$splittingProbs$Splitting_probability) + 2 * sd(distance$splittingProbs$Splitting_probability) ))
##Note that the way the aggregatedBranchingProbabilities are computed all pairs of cells from the same cluster are
## taken into account. This has the effect that clusters with more cells would be counted more often and contribute more
## to the shape of the final distribution. This is no problem right now as we only aggregate counts from clusters
## of the same size, it is however the potential source of a future bug!!
plot(ggplot(data.frame(x = distance$aggregatedBranchingProbabilities), aes(x = x)) +
geom_histogram(binwidth = 0.01))
print(data.frame(clusterSize = clusterSize, Cutoff = quantile(distance$aggregatedBranchingProbabilities, probs = 0.95, names = FALSE)[1] ))
cutoffsBranchingProbabilities <- rbind(cutoffsBranchingProbabilities, data.frame(clusterSize = clusterSize, Cutoff = quantile(distance$aggregatedBranchingProbabilities, probs = 0.95, names = FALSE)[1] ))
})
}
## Rows: 20188 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (1): Tree
## dbl (4): LogScore, SequencingErrorRate, DropoutRate, LogTau
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 557 Columns: 80
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (3): X1, X3, X4
## dbl (77): X2, X5, X6, X7, X8, X9, X10, X11, X12, X13, X14, X15, X16, X17, X1...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 38 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (2): Cluster, Description
## dbl (3): CellCount, TCs, WBCs
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## [1] "Computing genomic distances of leaves: 71 70"
## [1] "Computing the posterior distribution"
## [1] "Computing genomic distances of leaves: 73 72"
## [1] "Computing the posterior distribution"
## [1] "Computing genomic distances of leaves: 75 74"
## [1] "Computing the posterior distribution"
## [1] "Computing genomic distances of leaves: 77 76"
## [1] "Computing the posterior distribution"
## clusterSize Cutoff
## 1 2 0.9999968
## Rows: 19114 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (1): Tree
## dbl (4): LogScore, SequencingErrorRate, DropoutRate, LogTau
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 557 Columns: 78
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (3): X1, X3, X4
## dbl (75): X2, X5, X6, X7, X8, X9, X10, X11, X12, X13, X14, X15, X16, X17, X1...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 37 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (2): Cluster, Description
## dbl (3): CellCount, TCs, WBCs
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## [1] "Computing genomic distances of leaves: 71 70"
## [1] "Computing the posterior distribution"
## [1] "Computing genomic distances of leaves: 74 73"
## [1] "Computing the posterior distribution"
## [1] "Computing genomic distances of leaves: 77 76"
## [1] "Computing the posterior distribution"
## clusterSize Cutoff
## 1 3 0.9998601
## Rows: 16812 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (1): Tree
## dbl (4): LogScore, SequencingErrorRate, DropoutRate, LogTau
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 557 Columns: 76
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (3): X1, X3, X4
## dbl (73): X2, X5, X6, X7, X8, X9, X10, X11, X12, X13, X14, X15, X16, X17, X1...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 36 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (2): Cluster, Description
## dbl (3): CellCount, TCs, WBCs
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## [1] "Computing genomic distances of leaves: 71 70"
## [1] "Computing the posterior distribution"
## [1] "Computing genomic distances of leaves: 75 74"
## [1] "Computing the posterior distribution"
## clusterSize Cutoff
## 1 4 0.9991121
## Rows: 17901 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (1): Tree
## dbl (4): LogScore, SequencingErrorRate, DropoutRate, LogTau
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 557 Columns: 76
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (3): X1, X3, X4
## dbl (73): X2, X5, X6, X7, X8, X9, X10, X11, X12, X13, X14, X15, X16, X17, X1...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Rows: 36 Columns: 5
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (2): Cluster, Description
## dbl (3): CellCount, TCs, WBCs
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## [1] "Computing genomic distances of leaves: 71 70"
## [1] "Computing the posterior distribution"
## [1] "Computing genomic distances of leaves: 76 75"
## [1] "Computing the posterior distribution"
## clusterSize Cutoff
## 1 5 0.9706048
Get the relevant statistics for each of the clusters of a dataset and output numbers of oligoclonal clusters:
nTumorClusters <- 0
nOligoclonalClusters1 <- 0
nOligoclonalClusters2 <- 0
splittingSummary1 <- data.frame(Color = vector(), Oligoclonal = vector(), ClusterSize = vector())
splittingSummary2 <- data.frame(Color = vector(), Oligoclonal = vector(), ClusterSize = vector())
for(clusterSize in 2:5){
try({
clusterColor <- sampleDescription %>%
filter(WBC ==0 & color != 'gray93') %>%
group_by(color) %>%
filter(n() == clusterSize) %>%
pull(color) %>%
unique()
for(color in clusterColor){
distance <- computeClusterSplits(sampleDescription, postSampling, treeName, nCells,
nMutations, nClusters,
alleleCount,
mutatedReadCounts, totalReadCounts,
nMutationSamplingEvents = nMutationSamplingEvents, nTreeSamplingEvents = nTreeSamplingEvents,
cellPairSelection = c(color))
splittingProbs <- mean(distance$splittingProbs$Splitting_probability)
branchingProbs <- mean(distance$aggregatedBranchingProbabilities)
nTumorClusters <- nTumorClusters + 1
oligoclonal <- FALSE
print(clusterSize)
print(cutoffsSplittingProbs[(cutoffsSplittingProbs$clusterSize == clusterSize), 2])
if(splittingProbs > (cutoffsSplittingProbs[(cutoffsSplittingProbs$clusterSize == clusterSize), 2])){
nOligoclonalClusters1 <- nOligoclonalClusters1 + 1
oligoclonal <- TRUE
}
splittingSummary1 <- rbind(splittingSummary1, data.frame(Color = color, Oligoclonal = oligoclonal, ClusterSize = clusterSize))
oligoclonal <- FALSE
if(branchingProbs > cutoffsBranchingProbabilities[(cutoffsBranchingProbabilities$clusterSize == clusterSize), 2]){
nOligoclonalClusters2 <- nOligoclonalClusters2 + 1
oligoclonal <- TRUE
}
splittingSummary2 <- rbind(splittingSummary2, data.frame(Color = color, Oligoclonal = oligoclonal, ClusterSize = clusterSize))
}
})
}
## [1] "Computing genomic distances of leaves: 5 4"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 7 6"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 9 8"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 18 17"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 28 27"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 32 31"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 41 40"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 43 42"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 45 44"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 48 47"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 54 53"
## [1] "Computing the posterior distribution"
## [1] 2
## [1] 1.004274
## [1] "Computing genomic distances of leaves: 1 0"
## [1] "Computing the posterior distribution"
## [1] 3
## [1] 0.9979337
## [1] "Computing genomic distances of leaves: 11 10"
## [1] "Computing the posterior distribution"
## [1] 3
## [1] 0.9979337
## [1] "Computing genomic distances of leaves: 21 20"
## [1] "Computing the posterior distribution"
## [1] 3
## [1] 0.9979337
## [1] "Computing genomic distances of leaves: 25 24"
## [1] "Computing the posterior distribution"
## [1] 3
## [1] 0.9979337
## [1] "Computing genomic distances of leaves: 34 33"
## [1] "Computing the posterior distribution"
## [1] 3
## [1] 0.9979337
## [1] "Computing genomic distances of leaves: 38 37"
## [1] "Computing the posterior distribution"
## [1] 3
## [1] 0.9979337
## [1] "Computing genomic distances of leaves: 67 66"
## [1] "Computing the posterior distribution"
## [1] 3
## [1] 0.9979337
## [1] "Computing genomic distances of leaves: 14 13"
## [1] "Computing the posterior distribution"
## [1] 4
## [1] 0.9887489
## [1] "Computing genomic distances of leaves: 50 49"
## [1] "Computing the posterior distribution"
## [1] 4
## [1] 0.9887489
## [1] "Computing genomic distances of leaves: 63 62"
## [1] "Computing the posterior distribution"
## [1] 4
## [1] 0.9887489
## [1] "Computing genomic distances of leaves: 56 55"
## [1] "Computing the posterior distribution"
## [1] 5
## [1] 0.9914817
numberOfCancerClusters <- sampleDescription %>%
filter(WBC ==0 & color != 'gray93') %>%
group_by(color) %>%
filter(n() > 1) %>%
pull(color) %>%
unique() %>% length()
print(sprintf('%d out of %d clusters were found to be oligoclonal in %s, using method 1', nOligoclonalClusters1, numberOfCancerClusters, treeName))
## [1] "0 out of 22 clusters were found to be oligoclonal in Br16_AC, using method 1"
print(sprintf('%d out of %d clusters were found to be oligoclonal in %s, using method 2', nOligoclonalClusters2, numberOfCancerClusters, treeName))
## [1] "0 out of 22 clusters were found to be oligoclonal in Br16_AC, using method 2"
print(splittingSummary1)
## Color Oligoclonal ClusterSize
## 1 sandybrown FALSE 2
## 2 skyblue3 FALSE 2
## 3 thistle FALSE 2
## 4 lightslateblue FALSE 2
## 5 mistyrose FALSE 2
## 6 powderblue FALSE 2
## 7 greenyellow FALSE 2
## 8 khaki3 FALSE 2
## 9 darkseagreen4 FALSE 2
## 10 plum FALSE 2
## 11 navajowhite2 FALSE 2
## 12 lightcoral FALSE 3
## 13 lemonchiffon FALSE 3
## 14 deeppink FALSE 3
## 15 mediumaquamarine FALSE 3
## 16 steelblue FALSE 3
## 17 paleturquoise3 FALSE 3
## 18 darkslategray FALSE 3
## 19 violetred3 FALSE 4
## 20 yellowgreen FALSE 4
## 21 cadetblue FALSE 4
## 22 crimson FALSE 5
print(splittingSummary2)
## Color Oligoclonal ClusterSize
## 1 sandybrown FALSE 2
## 2 skyblue3 FALSE 2
## 3 thistle FALSE 2
## 4 lightslateblue FALSE 2
## 5 mistyrose FALSE 2
## 6 powderblue FALSE 2
## 7 greenyellow FALSE 2
## 8 khaki3 FALSE 2
## 9 darkseagreen4 FALSE 2
## 10 plum FALSE 2
## 11 navajowhite2 FALSE 2
## 12 lightcoral FALSE 3
## 13 lemonchiffon FALSE 3
## 14 deeppink FALSE 3
## 15 mediumaquamarine FALSE 3
## 16 steelblue FALSE 3
## 17 paleturquoise3 FALSE 3
## 18 darkslategray FALSE 3
## 19 violetred3 FALSE 4
## 20 yellowgreen FALSE 4
## 21 cadetblue FALSE 4
## 22 crimson FALSE 5